Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18839
    Prev
    Next
    INDEX
    Explanations

    plans or intentions for actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    665
    +0.14
    0.7%
    421
    +0.12
    0.6%
    641
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.03
    272
    +0.12
    0.03
    421
    +0.10
    0.03
    Negative Logits
    govtrack
    -0.74
    inas
    -0.70
    athi
    -0.69
    bour
    -0.68
    avery
    -0.67
    aghd
    -0.65
    mint
    -0.64
    osi
    -0.63
    tha
    -0.63
    bery
    -0.62
    POSITIVE LOGITS
    paren
    1.10
     Parenthood
    1.07
     accordingly
    0.88
    escape
    0.86
     ahead
    0.85
     trips
    0.83
     beforehand
    0.83
     obs
    0.82
     vacations
    0.80
     meals
    0.79
    Activations Density 0.045%

    No Known Activations